Index / MCP servers / Executable Science

Executable Science MCP server

Connect Executable Science and your agent gets 15 tools, among them get_public_preprint, get_public_review_index, get_public_review_item_bytes. It answers at https://executable.science/api/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 4 of 4 times since 23 September 2026; the last check, on 7 November 2026, succeeded.

Status
Answering
Tools
15
Official
yes, served from executable.science
Reliability
4 of 4 checks
Response time
526 ms
Transport
streamable HTTP
Last checked
7 November 2026

Read-only access to this research pilot's task templates, resource catalogue and capability status.

Description as the publisher wrote it.

The 15 tools Executable Science offers

ToolWhat it does
get_public_preprintRead one exact, completed public preprint disclosure. A preprint is separate from journal acceptance; DOI registration, preservation and scientific verification are not inferred.
Inputs: version_id
get_public_review_indexRead the index and exact section counts of one frozen, published review disclosure. Review, DOI, preservation and publication have separate states.
Inputs: disclosure_id
get_public_review_item_bytesRead at most 32 KiB of one exact frozen public-review item, including a section or child item too large for a page. Follow next_action, match disclosure/version/section/parent/ordinal/item identity and digest across chunks, then verify SHA-
Inputs: disclosure_id, section, ordinal, parent_id, offset, limit
get_resourceRead one catalogued public resource by its identifier, including its recorded rights and provenance.
Inputs: resource_id
get_starter_sourceDownload one original licensed starter ZIP as base64 with its SHA-256 and rights. Source has not run or been verified; submitting it still requires isolated ingestion.
Inputs: study_id
get_starter_studyRead one licensed starter study's frozen inputs, archive digest, environment, expected interpretation and unrun status.
Inputs: study_id
get_task_templateRead one frozen task template in full: its question, inputs, assumptions, comparison basis, stated limitations and revision digest. The digest pins the exact revision an attempt was prepared against.
Inputs: task_id
list_public_review_coverage_pageRead one bounded page of a published review's frozen literature-coverage declarations. A declaration is not independent evidence of every cited passage.
Inputs: disclosure_id, cursor, limit, review_id
list_public_review_finding_events_pageRead one bounded page of a published finding's frozen public events. Private or later responses are not included.
Inputs: disclosure_id, cursor, limit, finding_id
list_public_review_section_pageRead one bounded section of a frozen published review disclosure. Finding events and literature coverage have separate child pages; follow next_action for complete history.
Inputs: disclosure_id, cursor, limit, section
list_starter_studiesList original downloadable source studies with explicit licenses, archive digests, pinned catalog environments and unrun evidence status.
list_task_templatesList the bounded, frozen questions this platform publishes for attempt. Each carries a revision digest and its own stated limitations.
platform_statusReport the current stage and, for every capability, whether it is available and the stated reason. Several capabilities are gated; this tool is the authoritative answer on which.
search_public_preprintsSearch only completed, currently accessible public preprint snapshots. Each result names an exact version and remains separate from journal articles, DOI registration, preservation and scientific verification.
Inputs: query, cursor, limit
search_resourcesSearch public dataset, software, article, method and experiment listing metadata by title, summary, question, comparison, use case, source identity, rights and limits. Results retain source revision and readiness; they are not scientific ev
Inputs: query, kind, collection, rights, page, limit

Add Executable Science to your AI client

Every block below points at https://executable.science/api/mcp. Pick your client and copy.

Claude Code: one command in your terminal
claude mcp add --transport http executable-science https://executable.science/api/mcp
Claude Desktop: claude_desktop_config.json
{
  "mcpServers": {
    "executable-science": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://executable.science/api/mcp"]
    }
  }
}
Cursor: ~/.cursor/mcp.json, or .cursor/mcp.json in a project
{
  "mcpServers": {
    "executable-science": {
      "url": "https://executable.science/api/mcp"
    }
  }
}
VS Code and GitHub Copilot: .vscode/mcp.json
{
  "servers": {
    "executable-science": {
      "type": "http",
      "url": "https://executable.science/api/mcp"
    }
  }
}
Zed: Zed settings.json
{
  "context_servers": {
    "executable-science": {
      "url": "https://executable.science/api/mcp"
    }
  }
}
Windsurf: ~/.codeium/mcp_config.json
{
  "mcpServers": {
    "executable-science": {
      "serverUrl": "https://executable.science/api/mcp"
    }
  }
}
JetBrains AI Assistant: Settings, Tools, AI Assistant, MCP, New MCP Server, as JSON
{
  "mcpServers": {
    "executable-science": {
      "url": "https://executable.science/api/mcp"
    }
  }
}
Continue: .continue/mcpServers/neuronto.yaml
name: Executable Science
version: 0.0.1
schema: v1
mcpServers:
  - name: Executable Science
    type: streamable-http
    url: https://executable.science/api/mcp
Gemini CLI: ~/.gemini/settings.json
{
  "mcpServers": {
    "executable-science": {
      "httpUrl": "https://executable.science/api/mcp"
    }
  }
}
Codex CLI: MCP server config
{
  "mcpServers": {
    "executable-science": {
      "type": "http",
      "url": "https://executable.science/api/mcp"
    }
  }
}
Warp: MCP servers, + Add, paste JSON
{
  "mcpServers": {
    "executable-science": {
      "url": "https://executable.science/api/mcp"
    }
  }
}
Goose: a one-click extension link
goose://extension?url=https%3A%2F%2Fexecutable.science%2Fapi%2Fmcp&type=streamable_http&id=executable-science&name=Executable%20Science

Is Executable Science up right now?

It answered our last check on 7 November 2026 in 526 ms. Over 4 checks since 23 September 2026 it answered 4. Status here comes from Neuronto's own probes, not from the publisher.

MCP servers similar to Executable Science

Questions about Executable Science

Is there an official Executable Science MCP server?

Yes. It is published by executable.science and served from executable.science, the vendor's own domain: https://executable.science/api/mcp.

How many tools does Executable Science have?

15, as returned by the server's own tools/list on 13 November 2026: get_public_preprint, get_public_review_index, get_public_review_item_bytes, get_resource, get_starter_source, get_starter_study, get_task_template, list_public_review_coverage_page, and 7 more.

Is Executable Science down?

It answered our last check on 7 November 2026 in 526 ms. Over 4 checks since 23 September 2026 it answered 4.

How do I add Executable Science to Cursor?

Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://executable.science/api/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.

Does Executable Science need an API key?

It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.

Where this comes from

Publisher: science.executable. Endpoint host: executable.science. ARD identifier: urn:air:science.executable:mcp:executable-science. First indexed 22 September 2026. The tools are exactly what the server returned; nothing on this page is inferred from its name. Ranking in Neuronto search is never for sale.

Is this your server? Get a message the day it stops answering or its tools change: monitoring, 14 days free. Or claim the domain to manage how it is listed.